INDEX

Explanations

references to organizations and entities involved in projects or reports

oai_token-act-pair · gpt-4o-mini Triggered by @bot

organizations and their actions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

richTextPanel

-0.67

IntoConstraints

-0.55

 <=",

-0.53

AISSEE

-0.52

 ComVisible

-0.49

 AssemblyVersion

-0.49

 متعلقه

-0.49

Clik

-0.49

StructEnd

-0.48

 popping

-0.47

POSITIVE LOGITS

 expects

0.40

ఔ

0.37

tilha

0.36

тім

0.36

 esperan

0.36

 pihaknya

0.35

ztály

0.35

 însă

0.35

appcompat

0.34

 Exacts

0.34

Activations Density 0.024%

references to organizations and entities involved in projects or reports

organizations and their actions

No Comments

No Known Activations